suppressPackageStartupMessages(library(tidyverse))
library(targets)
library(tarchetypes)
library(DT)knitr::opts_knit$set(root.dir = "../../")df_mm <- tar_read(df_mm)
df_mm %>%
select(category_id, activity_id_new, has_finding, everything())## # A tibble: 4,055 × 185
## category_id activity_id_new has_finding start_date n_visit n_unsch_visit
## <chr> <chr> <chr> <date> <dbl> <dbl>
## 1 cnsn 00001 yes 2015-01-01 732 26
## 2 cnsn 00003 yes 2014-01-01 NA NA
## 3 cnsn 00004 yes 2015-01-01 181 33
## 4 cnsn 00006 yes 2014-01-01 0 0
## 5 cnsn 00008 yes 2015-01-01 114 0
## 6 cnsn 00009 yes 2015-01-01 297 0
## 7 cnsn 00012 yes 2015-01-01 446 7
## 8 cnsn 00013 yes 2015-01-01 688 65
## 9 cnsn 00015 yes 2015-01-01 141 17
## 10 cnsn 00016 yes 2015-01-01 0 0
## # … with 4,045 more rows, and 179 more variables: n_sched_visit <dbl>,
## # ratio_unsch_visit <dbl>, ratio_unsch_visit_rnk <dbl>, n_ae <dbl>,
## # n_sae <dbl>, ae_per_visit <dbl>, sae_per_visit <dbl>,
## # ae_per_visit_rnk <dbl>, sae_per_visit_rnk <dbl>,
## # median_ae_reporting_delay <dbl>, mean_ae_reporting_delay <dbl>,
## # max_ae_reporting_delay <dbl>, median_sae_reporting_delay <dbl>,
## # mean_sae_reporting_delay <dbl>, max_sae_reporting_delay <dbl>,
## # n_patients <dbl>, therapeutic_area <chr>, n_active_sites_pi_yy <dbl>,
## # n_active_sites_pi_yy_rnk <dbl>, n_active_trials_at_site_in_ta_yy <dbl>,
## # n_active_trials_at_site_in_ta_yy_rnk <dbl>, time_on_study_dd <dbl>,
## # dev_data_available <chr>, n_maj_dev <dbl>, n_min_dev <dbl>,
## # n_maj_dev_per_daysonstudy <dbl>, n_min_dev_per_daysonstudy <dbl>,
## # n_maj_dev_per_daysonstudy_rnk <dbl>, n_min_dev_per_daysonstudy_rnk <dbl>,
## # issue_data_available <chr>, mean_iss_completion_time <dbl>,
## # median_iss_completion_time <dbl>, max_iss_completion_time <dbl>,
## # n_iss_open <dbl>, n_iss_open_per_pat <dbl>, n_iss_due <dbl>,
## # n_iss_compl <dbl>, n_iss_compl_per_daysonstudy <dbl>, n_iss_late <dbl>,
## # n_iss_cnsn_open <dbl>, n_iss_cnsn_due <dbl>, n_iss_cnsn_compl <dbl>,
## # n_iss_cnsn_late <dbl>, n_iss_dtin_open <dbl>, n_iss_dtin_due <dbl>,
## # n_iss_dtin_compl <dbl>, n_iss_dtin_late <dbl>, n_iss_ptpe_open <dbl>,
## # n_iss_ptpe_due <dbl>, n_iss_ptpe_compl <dbl>, n_iss_ptpe_late <dbl>,
## # n_iss_srpo_open <dbl>, n_iss_srpo_due <dbl>, n_iss_srpo_compl <dbl>,
## # n_iss_srpo_late <dbl>, n_iss_spno_open <dbl>, n_iss_spno_due <dbl>,
## # n_iss_spno_compl <dbl>, n_iss_spno_late <dbl>, n_iss_sfty_open <dbl>,
## # n_iss_sfty_due <dbl>, n_iss_sfty_compl <dbl>, n_iss_sfty_late <dbl>,
## # n_iss_stdc_open <dbl>, n_iss_stdc_due <dbl>, n_iss_stdc_compl <dbl>,
## # n_iss_stdc_late <dbl>, screen_failure_ratio <dbl>, protocol_version <dbl>,
## # countrycode <chr>, region <chr>, subregion <chr>, is_engl_prim_lang <dbl>,
## # subregion_alt <chr>, is_apac <dbl>, is_eu_east <dbl>, is_eu <dbl>,
## # is_us_nz_ca_au <dbl>, is_sa <dbl>, is_afr <dbl>, prob_low_prob_ur <dbl>,
## # is_prob_ur_smp05 <dbl>, is_prob_ur_smp1 <dbl>, is_prob_ur_p5_p95 <dbl>,
## # is_prob_ur_grp95 <dbl>, is_prob_ur_grp75 <dbl>, studyphase <chr>,
## # is_pediatric <dbl>, blinding <chr>, comparison <chr>,
## # therapeuticarea <chr>, targetnumcountries <dbl>, randomization <chr>,
## # generalindication <chr>, is_dementia <dbl>, is_ad <dbl>, is_cancer <dbl>,
## # is_neuro_or_psychiatric <dbl>, is_autoimmune <dbl>,
## # distinct_unsch_visits <dbl>, …tibble(columns = colnames(df_mm)) %>%
DT::datatable()df_mm_bin <- tar_read(df_mm_bin)
df_mm_bin %>%
select(category_id, activity_id_new, has_finding, everything())## # A tibble: 4,055 × 861
## category_id activity_id_new has_finding nvisitLL nvisitML nvisitM nvisitMH
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 cnsn 00001 yes 0 0 0 1
## 2 cnsn 00003 yes 0 0 0 0
## 3 cnsn 00004 yes 0 0 1 0
## 4 cnsn 00006 yes 1 0 0 0
## 5 cnsn 00008 yes 0 1 0 0
## 6 cnsn 00009 yes 0 0 1 0
## 7 cnsn 00012 yes 0 0 0 1
## 8 cnsn 00013 yes 0 0 0 1
## 9 cnsn 00015 yes 0 1 0 0
## 10 cnsn 00016 yes 1 0 0 0
## # … with 4,045 more rows, and 854 more variables: nvisitHH <dbl>,
## # nvisitNA <dbl>, nunschvisitLL <dbl>, nunschvisitML <dbl>,
## # nunschvisitM <dbl>, nunschvisitMH <dbl>, nunschvisitHH <dbl>,
## # nunschvisitNA <dbl>, nschedvisitLL <dbl>, nschedvisitML <dbl>,
## # nschedvisitM <dbl>, nschedvisitMH <dbl>, nschedvisitHH <dbl>,
## # nschedvisitNA <dbl>, ratiounschvisitLL <dbl>, ratiounschvisitML <dbl>,
## # ratiounschvisitM <dbl>, ratiounschvisitMH <dbl>, ratiounschvisitHH <dbl>,
## # ratiounschvisitNA <dbl>, ratiounschvisitrnkLL <dbl>,
## # ratiounschvisitrnkML <dbl>, ratiounschvisitrnkM <dbl>,
## # ratiounschvisitrnkMH <dbl>, ratiounschvisitrnkHH <dbl>,
## # ratiounschvisitrnkNA <dbl>, naeLL <dbl>, naeML <dbl>, naeM <dbl>,
## # naeMH <dbl>, naeHH <dbl>, naeNA <dbl>, nsaeLL <dbl>, nsaeML <dbl>,
## # nsaeM <dbl>, nsaeMH <dbl>, nsaeHH <dbl>, nsaeNA <dbl>, aepervisitLL <dbl>,
## # aepervisitML <dbl>, aepervisitM <dbl>, aepervisitMH <dbl>,
## # aepervisitHH <dbl>, aepervisitNA <dbl>, saepervisitLL <dbl>,
## # saepervisitML <dbl>, saepervisitM <dbl>, saepervisitMH <dbl>,
## # saepervisitHH <dbl>, saepervisitNA <dbl>, aepervisitrnkLL <dbl>,
## # aepervisitrnkML <dbl>, aepervisitrnkM <dbl>, aepervisitrnkMH <dbl>,
## # aepervisitrnkHH <dbl>, aepervisitrnkNA <dbl>, saepervisitrnkLL <dbl>,
## # saepervisitrnkML <dbl>, saepervisitrnkM <dbl>, saepervisitrnkMH <dbl>,
## # saepervisitrnkHH <dbl>, saepervisitrnkNA <dbl>,
## # medianaereportingdelayLL <dbl>, medianaereportingdelayML <dbl>,
## # medianaereportingdelayM <dbl>, medianaereportingdelayMH <dbl>,
## # medianaereportingdelayHH <dbl>, medianaereportingdelayNA <dbl>,
## # meanaereportingdelayLL <dbl>, meanaereportingdelayML <dbl>,
## # meanaereportingdelayM <dbl>, meanaereportingdelayMH <dbl>,
## # meanaereportingdelayHH <dbl>, meanaereportingdelayNA <dbl>,
## # maxaereportingdelayLL <dbl>, maxaereportingdelayML <dbl>,
## # maxaereportingdelayM <dbl>, maxaereportingdelayMH <dbl>,
## # maxaereportingdelayHH <dbl>, maxaereportingdelayNA <dbl>,
## # mediansaereportingdelayLL <dbl>, mediansaereportingdelayML <dbl>,
## # mediansaereportingdelayM <dbl>, mediansaereportingdelayMH <dbl>,
## # mediansaereportingdelayHH <dbl>, mediansaereportingdelayNA <dbl>,
## # meansaereportingdelayLL <dbl>, meansaereportingdelayML <dbl>,
## # meansaereportingdelayM <dbl>, meansaereportingdelayMH <dbl>,
## # meansaereportingdelayHH <dbl>, meansaereportingdelayNA <dbl>,
## # maxsaereportingdelayLL <dbl>, maxsaereportingdelayML <dbl>,
## # maxsaereportingdelayM <dbl>, maxsaereportingdelayMH <dbl>,
## # maxsaereportingdelayHH <dbl>, maxsaereportingdelayNA <dbl>,
## # npatientsLL <dbl>, npatientsML <dbl>, …tibble(columns = colnames(df_mm_bin)) %>%
DT::datatable()Modelling coefficients have been preselected.
tar_read(df_form) %>%
DT::datatable()Indeces of modelling matrix that defines time series cross validation strategy.
tar_read(df_cv)## # A tibble: 45 × 4
## year_start_act category_id index_past index_next_year
## <dbl> <chr> <chr> <chr>
## 1 2011 cnsn 70,71,72,84,85,86,87,8… 155,170,171,172,173,174,1…
## 2 2012 cnsn 70,71,72,84,85,86,87,8… 211,229,231,234,241,242,2…
## 3 2013 cnsn 70,71,72,84,85,86,87,8… 2,4,306,307,308,309,310,3…
## 4 2014 cnsn 2,4,70,71,72,84,85,86,… 1,3,5,6,7,8,9,10,11,12,13…
## 5 2015 cnsn 1,2,3,4,5,6,7,8,9,10,1… 30,34,45,46,47,48,49,50,5…
## 6 2016 cnsn 1,2,3,4,5,6,7,8,9,10,1… 98,99,100,101,102,103,106…
## 7 2017 cnsn 1,2,3,4,5,6,7,8,9,10,1… 228,238,239,240,248,251,2…
## 8 2018 cnsn 1,2,3,4,5,6,7,8,9,10,1… 358,359,360,361,362,363,3…
## 9 2019 cnsn 1,2,3,4,5,6,7,8,9,10,1… 368,805,808
## 10 2015 dtin 5678,5679,5680,5681,56… 5698,5714,5715,5724,5725,…
## # … with 35 more rowsAll names of all features and their variations.
tar_read(df_feat_lookup) %>%
DT::datatable()All finding statements mapped to clinical impact factors.
tar_read(df_cat_lookup) %>%
DT::datatable()